Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    documentation comments or decorators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    minIndex
    0.64
    yscrapers
    0.63
    Anno
    0.60
    woman
    0.58
    RAIN
    0.57
    jfif
    0.57
    BankAccount
    0.56
    BIN
    0.54
    あとは
    0.53
    Очень
    0.52
    POSITIVE LOGITS
     stupe
    0.68
     evaded
    0.65
     behest
    0.64
    क
    0.62
    鐗
    0.62
    ك
    0.61
    غ
    0.61
     inhibit
    0.61
    cemic
    0.61
    ється
    0.61
    Act Density 0.004%

    No Known Activations